Journal of Diabetes Science and Technology最新文献

{"title":"'Impossible' Insulin to C-Peptide Ratios are Common in Insulin-Free Pre-term NICU Infants: Antibodies Act as a Storage Medium.","authors":"J Geoffrey Chase, Helen D Shannon","doi":"10.1177/19322968261439151","DOIUrl":"10.1177/19322968261439151","url":null,"abstract":"","PeriodicalId":15475,"journal":{"name":"Journal of Diabetes Science and Technology","volume":" ","pages":"1489-1490"},"PeriodicalIF":4.9,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13061843/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147633385","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The Impact of Virtual Consultations on Quality of Care for Patients With Type 2 Diabetes: A Systematic Review and Meta-Analysis.","authors":"Reham Aldakhil, Geva Greenfield, Elena Lammila-Escalera, Liliana Laranjo, Benedict W J Hayhoe, Azeem Majeed, Ana Luísa Neves","doi":"10.1177/19322968251316585","DOIUrl":"10.1177/19322968251316585","url":null,"abstract":"<p><p>BackgroundVirtual consultations (VC) have transformed healthcare delivery, offering a convenient and effective way to manage chronic conditions such as Type 2 Diabetes (T2D). This systematic review and meta-analysis evaluated the impact of VC on the quality of care provided to patients with T2D, mapping it across the six domains of the US National Academy of Medicine (NAM) quality-of-care framework (ie, effectiveness, efficiency, patient-centeredness, timeliness, safety, and equity).MethodsA systematic search was conducted in PubMed/MEDLINE, Cochrane, Embase, CINAHL, and Web of Science for the period between January 2010 and December 2024. Eligible studies involved adult T2D patients, evaluated synchronous VCs, and reported outcomes relevant to NAM quality domains. Two independent reviewers performed screening, and studies were assessed using the Mixed Methods Appraisal Tool (MMAT). A narrative synthesis was conducted for each quality domain, and a meta-analysis of HbA1c levels was performed using random-effects models.ResultsIn total, 15 studies involving 821 014 participants were included. VCs were comparable with face-to-face care in effectiveness, efficiency, patient-centeredness, and timeliness, with improvements in accessibility and patient satisfaction. Mixed results were found for safety due to limitations in physical assessments, and for equity, with older adults and those with lower digital literacy facing more challenges. The meta-analysis showed no significant difference in HbA1c reduction between VCs and face-to-face (standardized mean difference [SMD] = -0.31, 95% confidence interval [CI]: -0.71 to 0.09, <i>P</i> = 0.12).ConclusionVCs offer a promising alternative to in-person care, but addressing digital disparities and improving access for older adults are essential for maximizing VC potential.</p>","PeriodicalId":15475,"journal":{"name":"Journal of Diabetes Science and Technology","volume":" ","pages":"1435-1449"},"PeriodicalIF":4.9,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11833803/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143441092","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comparison of the Effect of Teleconsultations, Hybrid Visits, and In-Person Visits on Glycemic and Metabolic Parameters Among Individuals With Type 2 Diabetes in India.","authors":"Anandakumar Amutha, Shyama Reji, Ramamurthy Hema Aarthi, Srinivas Keertan Rao, S Ganesan, Saravanan Jebarani, Gangadhara Praveen, Ranjit Unnikrishnan, Viswanathan Mohan, Ranjit Mohan Anjana","doi":"10.1177/19322968251319333","DOIUrl":"10.1177/19322968251319333","url":null,"abstract":"<p><strong>Aim: </strong>We compared biochemical and clinical data of individuals with type 2 diabetes (T2D) who opted for only teleconsultation (ie, no in-person visit at all), hybrid visits (combining home blood tests and in-person consultation), and fully in-person visits (both tests and consultation in person) at a tertiary care diabetes center.</p><p><strong>Methods: </strong>In this observational cohort study, we retrieved demographic, anthropometric, and biochemical data of 8197 individuals with T2D who sought diabetes care between 2021 and 2023 (384 participants with only teleconsultations, 721 with hybrid visits, and 7092 with fully in-person visits) from the electronic medical records of a chain of tertiary diabetes care centers across India.</p><p><strong>Results: </strong>Individuals who opted for teleconsultation had a shorter duration of diabetes compared with those who opted for hybrid or fully in-person visits. Although participants who opted for a teleconsultation had better glycemic and lipid control at baseline, those who underwent hybrid and in-person visits showed greater improvements in fasting plasma glucose, glycated hemoglobin (A1c), and LDL cholesterol (LDL-C) during follow-up. Improvements in overall ABC target achievement (<u>A</u>1c, <u>B</u>lood pressure, and <u>L</u>DL-C) were greater in participants who had in-person visits compared with the other two groups.</p><p><strong>Conclusion: </strong>While teleconsultation is a useful complement to in-person visits, the latter results in better glycemic and lipid control, perhaps due to more effective engagement with the diabetes care team.</p>","PeriodicalId":15475,"journal":{"name":"Journal of Diabetes Science and Technology","volume":" ","pages":"1360-1369"},"PeriodicalIF":4.9,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11840818/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143449197","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Predicting Postprandial Glycemic Responses With Limited Data in Type 1 and Type 2 Diabetes.","authors":"Yiheng Shen, Euiji Choi, Samantha Kleinberg","doi":"10.1177/19322968251321508","DOIUrl":"10.1177/19322968251321508","url":null,"abstract":"<p><strong>Background: </strong>A core challenge in managing diabetes is predicting glycemic responses to meals. Prior work identified significant interindividual variation in responses and developed personalized forecasts. However, intraindividual variation is still not well understood, and the most accurate approaches require invasive microbiome data. We aimed to investigate (1) whether postprandial glycemic responses (PPGRs) can be predicted with limited data and (2) sources of intraindividual variation.</p><p><strong>Methods: </strong>We used data collected from 397 people with Type 1 Diabetes (T1DEXI) and 100 people with Type 2 Diabetes (ShanghaiT2DM) who wore continuous glucose monitors (CGMs) and logged meals. Using dietary, demographic, and temporal features, we predicted 2 hours PPGR, and peak 2 hours postprandial glucose rise (Glu_max). We evaluated the contribution of food features (eg, macronutrients, food category) and use of personal training data and investigated intraindividual variability in responses.</p><p><strong>Results: </strong>We achieved comparable accuracy to prior work for PPGR (T1DEXI R = 0.61, ShanghaiT2DM R = 0.72) and Glu_max (T1DEXI R = 0.64, ShanghaiT2DM R = 0.73), without using invasive data like microbiome. Including food category features led to higher accuracy than macronutrients alone. Analysis of glycemic responses to duplicate meals identified time of day (PPGR: T1DEXI <i>P</i> < .05 for lunch, ShanghaiT2DM <i>P</i> < .001 for lunch and dinner) and menstrual cycle (Glu_max: <i>P</i> < .05 for perimenstrual) as sources of variability.</p><p><strong>Conclusions: </strong>We demonstrate that in individuals with T1D and T2D, glycemic responses to meals can be predicted without personalized training data or invasive physiological data.</p>","PeriodicalId":15475,"journal":{"name":"Journal of Diabetes Science and Technology","volume":" ","pages":"1252-1265"},"PeriodicalIF":4.9,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11883769/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143556984","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"<i>Green</i> Diabetes: Already a Decisive Factor for or Against Technology for People Living With Diabetes?","authors":"Stefanie Hossmann, Aritz Lizoain, Timm Roos, Derek Brandt, Dominic Ehrmann, Bernhard Kulzer, Norbert Hermanns, Cordelia Trümpy, Michael Resl, Peter Diem, Javier Ampudia-Blasco, Julia K Mader, Lutz Heinemann","doi":"10.1177/19322968261436839","DOIUrl":"10.1177/19322968261436839","url":null,"abstract":"<p><strong>Background: </strong>The rapid rise of diabetes technology has markedly improved glycemic outcomes, quality of life, and empowerment of people living with diabetes (PwD). However, the increased use of devices such as continuous glucose monitoring systems, insulin pumps, and smart pens has also introduced significant environmental concerns, contributing to waste from plastic, electronics (e-waste) and packaging, and greenhouse gas emissions.</p><p><strong>Methods: </strong>In this paper, we describe results from an online survey conducted in Germany, Austria, and Switzerland, between November and December 2024, focused on the level of concern PwD have, regarding the environmental impacts of single-use medical device, supplies and packaging, resulting from diabetes treatment, and whether these considerations influence technology choices.</p><p><strong>Results: </strong>Among 1934 PwD surveyed, 1332 (69%) favored more reusable devices, and 865 (45%) expressed concern about packaging waste. However, environmental factors ranked far below safety, effectiveness, and usability when selecting diabetes technologies.</p><p><strong>Conclusions: </strong>Expecting PwD to drive substantial environmental improvements is therefore neither realistic nor fair given prevailing priorities on safety and outcomes. Meaningful progress toward greener diabetes care will depend on manufacturers, policymakers, and healthcare systems embracing eco-design, establishing recycling infrastructure, and integrating sustainability into regulatory and reimbursement frameworks. Only through coordinated efforts can optimal diabetes management be achieved alongside environmental stewardship.</p>","PeriodicalId":15475,"journal":{"name":"Journal of Diabetes Science and Technology","volume":" ","pages":"1117-1121"},"PeriodicalIF":4.9,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13070107/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147654365","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Systematic Review of Continuous Glucose Monitor Accuracy in the Hypoglycemia Range for Non-Critical Care Ward Hospitalized People Living With Diabetes.","authors":"Nicole Prince, Timothy Ramsay, Risa Shorr, Rémi Rabasa-Lhoret, Cathy J Sun","doi":"10.1177/19322968251412482","DOIUrl":"10.1177/19322968251412482","url":null,"abstract":"<p><p>In-hospital standard of care for people living with diabetes (PLWD) is based on capillary blood glucose to activate hypoglycemia treatment protocols. PLWD on non-critical care wards often prefer to keep their continuous glucose monitor (CGM) on for their sense of agency. This systematic review assessed the CGM accuracy in the hypoglycemic range for these PLWD. Databases were searched from 2012 to August 2025. We included studies of adult PLWD on non-critical care wards, with CGM levels below 70 mg/dL (3.9 mmol/L) that were compared with paired reference blood glucose levels. Nine included studies reported on 465 hypoglycemic CGM and reference blood glucose pairs. The mean and median absolute relative differences ranged from 7.6% to 53.3%, and from 11.7% to 38.5%, respectively. The methods for pairing CGM with reference blood glucose varied. In eight studies, the mean absolute relative differences between hypoglycemia range CGM and paired reference blood glucose results were greater than 15%. These high mean absolute relative differences suggest that hypoglycemic range CGM results are too inaccurate to guide in-hospital diabetes therapy.</p>","PeriodicalId":15475,"journal":{"name":"Journal of Diabetes Science and Technology","volume":" ","pages":"1389-1395"},"PeriodicalIF":4.9,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12861416/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146093228","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Continuous Glucose Monitoring Metrics for Predicting Adverse Neonatal Outcomes in Individuals Undergoing Gestational Diabetes Screening.","authors":"Caleb Griffiths, Rafael Bravo Santos, Sarah A Wernimont, Julie Anderson, Megan Kristan, Erika S Helgeson, Lisa S Chow, Michal Fishel Bartal","doi":"10.1177/19322968261461603","DOIUrl":"10.1177/19322968261461603","url":null,"abstract":"<p><strong>Objectives: </strong>This study evaluates whether continuous glucose monitoring (CGM) metrics predict adverse neonatal outcomes among individuals undergoing gestational diabetes screening. Building on findings by Fishel Bartal et al, who reported an association between ≥10% time above 140 mg/dL and a composite neonatal outcome, this analysis examines 13 additional CGM-derived measures reflecting glycemic variability (GV) and glycemic extremes.</p><p><strong>Methods: </strong>Eighty-four pregnant individuals wore CGM devices for 10 days following a 1-hour 50 g glucose challenge test. Generalized estimating equation logistic regression models assessed associations between CGM metrics and a composite neonatal outcome consisting of large-for-gestational-age birth, need for intravenous glucose treatment, or shoulder dystocia. Model discrimination was quantified using the area under the receiver operating characteristic curve (AUROC).</p><p><strong>Results: </strong>Several CGM measures-including mean glucose, standard deviation (SD), maximum glucose, %Time >140 mg/dL, %Time >120 mg/dL, glucose management indicator (GMI), mean of daily differences (MODD), mean amplitude of glycemic excursions (MAGE), area under the CGM curve (AUC-CGM), and high blood glucose index (HBGI)-were significantly associated with adverse neonatal outcomes (<i>P</i> < .05). Metrics demonstrating higher discrimination than the original ≥10% time-above-range measure (AUROC = 0.643) included SD (0.656), MAGE (0.665), mean glucose (0.676), GMI (0.676), maximum glucose (0.683), %Time >120 mg/dL (0.683), AUC-CGM (0.692), HBGI (0.701), and %Time >140 mg/dL (0.703).</p><p><strong>Conclusions: </strong>Continuous glucose monitoring metrics reflecting sustained or high-level hyperglycemia, rather than GV-focused metrics, more strongly predicted adverse neonatal outcomes. These findings suggest that persistent or extreme maternal glucose elevations, rather than variability alone, may drive neonatal risk and support refining CGM-based screening approaches in pregnancy.</p>","PeriodicalId":15475,"journal":{"name":"Journal of Diabetes Science and Technology","volume":" ","pages":"19322968261461603"},"PeriodicalIF":4.9,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13323036/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148361138","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automated Insulin Delivery Systems: Impact on Clinical Practice, Discontinuation, Rejection, and Reasons for Not Managing Well.","authors":"Timm Roos, Norbert Hermanns, Lutz Heinemann, Dominic Ehrmann, Derek Brandt, Julia K Mader, Michael Resl, Peter Diem, Cordelia Trümpy, Jose Fernando Garcia-Tirado, Bernhard Kulzer","doi":"10.1177/19322968261441314","DOIUrl":"10.1177/19322968261441314","url":null,"abstract":"<p><strong>Background: </strong>Automated insulin delivery (AID) systems can significantly improve glycemic outcomes in people with type 1 diabetes (PWT1D). Despite their clinical efficacy, little is known about their uptake in clinical care, or about the perspectives and experiences of health care professionals (HCPs) and people with diabetes (PWD) with this relatively new technology.Furthermore, research is limited on broader populations, such as people with type 2 diabetes (PWT2D) and cross-country comparisons.</p><p><strong>Methods: </strong>This study analyzes data from the dt-report 2025, a multinational online survey of PWD and HCPs from Germany, Austria, Switzerland, and Spain, which was conducted at the end of 2024. The surveys assessed, among others, AID relevance, indications, barriers, daily use, satisfaction, and support needs.</p><p><strong>Results: </strong>In total, 1294 HCPs and 2535 PWD from Germany, Austria, Switzerland, and Spain took part. Health care professionals identified fully closed-loop systems as the most promising future therapy. While 90% of PWT1D were seen as candidates for AID therapy, 55% of PWT2D on intensified insulin therapy were also considered likely to benefit. Nonetheless, 22% of eligible PWD rejected AID, citing device burden and general concerns regarding its usability. Health care professionals reported a discontinuation rate of 8%. Satisfaction with AID was generally high. Regression analyses identified technical problems, lack of trust, and unrealistic expectations as significant predictors of lower satisfaction and poorer management in PWD.</p><p><strong>Conclusion: </strong>Despite increasing user rates of AID systems, a significant proportion reports problems in managing this technology or aborting its use. Addressing reasons for this may increase the uptake in clinical care. There was also a positive view of HCPs on AID use in PWT2D.</p>","PeriodicalId":15475,"journal":{"name":"Journal of Diabetes Science and Technology","volume":" ","pages":"1091-1099"},"PeriodicalIF":4.9,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13153006/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147838631","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The Prevalence and Predictors of Improper Sharps Collection Practices Among People With Diabetes in Saudi Arabia.","authors":"Mohammed E Al-Sofiani, Ghadah Alsuwailem, Maee Barakeh, Ghaida Almarshoud, Alia Zawawi, Rawan Bakader","doi":"10.1177/19322968251318747","DOIUrl":"10.1177/19322968251318747","url":null,"abstract":"<p><strong>Background: </strong>Diabetes treatment requires the use of medical sharps for glycemic control. Improper sharps collection and disposal poses substantial threats to people with diabetes (PWD), health care professionals, the environment, and public health.</p><p><strong>Objectives: </strong>To identify the prevalence and predictors of improper sharps collection practices among PWD in Saudi Arabia.</p><p><strong>Methods: </strong>We surveyed 288 PWD at King Saud University Diabetes Center in Riyadh, Saudi Arabia, from September to October 2021. We asked questions about demographics, diabetes history, sharps collection practices, and prior education on proper sharps collection practices. We defined \"proper sharps collection\" as: using a designated sharps disposal container or homemade sealed container to collect sharps.</p><p><strong>Results: </strong>Of the PWD surveyed, 60% were women, 54% were ≥35 years old, and 53% had type 1 diabetes. Most respondents (80% and 72%) reported improper collection of needles and lancets, respectively. Approximately, 56% of needle users and 61% of lancet users reported that they had never received instructions on safe sharps disposal. Receiving education on safe sharps disposal practices was associated with a 66% reduction in the risk of improper sharps collection practices (odds ratio (OR) [95% confidence interval (CI)]: 0.34 [0.16-0.68]) after adjusting for age, gender, type and duration of diabetes, income, education, and nationality of the study participants. Among those who improperly dispose their needles, 67% thought their sharps collection practices were appropriate.</p><p><strong>Conclusions: </strong>Our findings highlight the high prevalence of unsafe sharps collection practices among PWD in Saudi Arabia, and how prior education on safe sharps collection practices can help address this environmental and public health threat. Policies to reduce diabetes-related waste, unify the approach to proper sharps collection and disposal, and promote safe disposal education are needed to achieve a sustainable and safe waste management system.</p>","PeriodicalId":15475,"journal":{"name":"Journal of Diabetes Science and Technology","volume":" ","pages":"1353-1359"},"PeriodicalIF":4.9,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11830154/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143425487","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Hypoglycemia Prediction in Type 1 Diabetes With Electrocardiography Beat Ensembles.","authors":"Mu-Ruei Tseng, Kathan Vyas, Anurag Das, Waris Quamer, Darpit Dave, Madhav Erranguntla, Carolina Villegas, Daniel DeSalvo, Siripoom McKay, Gerard Cote, Ricardo Gutierrez-Osuna","doi":"10.1177/19322968251319347","DOIUrl":"10.1177/19322968251319347","url":null,"abstract":"<p><strong>Introduction: </strong>Current methods to detect hypoglycemia in type 1 diabetes (T1D) require invasive sensors (ie, continuous glucose monitors, CGMs) that generally have low accuracy in the hypoglycemic range. A forward-looking alternative is to monitor physiological changes induced by hypoglycemia that can be measured non-invasively using, eg, electrocardiography (ECG). However, current methods require extraction of fiduciary points in the ECG signal (eg, to estimate QT interval), which is challenging in ambulatory settings.</p><p><strong>Methods: </strong>To address this issue, we present a machine-learning model that uses (1) convolutional neural networks (CNNs) to extract morphological information from raw ECG signals without the need to identify fiduciary points and (2) ensemble learning to aggregate predictions from multiple ECG beats. We evaluate the model on an experimental data set that contains ECG and CGM recordings over a period of 14 days from ten participants with T1D. We consider two testing scenarios, one that divides ECG data according to CGM readings (CGM-split) and another that divides ECG data on a day-to-day basis (day-split)Results:We find that models trained using CGM-splits tend to produce overly optimistic estimates of hypoglycemia prediction, whereas day-splits provide more realistic estimates, which are consistent with the intrinsic accuracy of CGM devices. More importantly, we find that aggregating predictions from multiple ECG beats using ensemble learning significantly improves predictions at the beat level, though these improvements have large inter-individual differences.</p><p><strong>Conclusion: </strong>Deep learning models and ensemble learning can extract and aggregate morphological information in ECG signals that is predictive of hypoglycemia. Using two validation procedures, we estimate an upper bound on the accuracy of ECG hypoglycemia prediction of 81% equal error rate and a lower bound of 60%. Further improvements may be achieved using big-data approaches that require longitudinal data from a large cohort of participants.</p>","PeriodicalId":15475,"journal":{"name":"Journal of Diabetes Science and Technology","volume":" ","pages":"1293-1301"},"PeriodicalIF":4.9,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11863193/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143501466","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}